Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

Standing at the bus stop, the cold wind whipped at Sophia’s face. She clutched her scarf tighter, a gesture of comfort against the biting chill. The cityscape blurred around her, the familiar buildings taking on an ethereal quality.

A name surfaced in her thoughts, a name she hadn't considered in years: Paul Reynolds, the boy who, in her teenage years, could make her feel like the smallest person in the world. He was listed as a therapist online, specialising in helping people with anxieties. The unexpected news hit her like a punch to the gut.

She remembered the way the leaves crunched underfoot, the crispness of the air. A feeling, something akin to a phantom limb, ached within her.

Emotion: nostalgic

Cluster: Nostalgia / Reflection
PC1 (Valence): 1.00 Positive
PC2 (Disposition): -1.93

Role in Research

This story is one of 1,000 stories generated for the emotion nostalgic. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 nostalgic stories, after denoising with neutral dialogue baselines, produces the nostalgic emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the nostalgic vector is projected through the unembedding matrix.

Promoted:
H0.677
L0.647
시절0.611
nostalgic0.609
fondly0.609
Suppressed:
--0.564
either-0.525
or-0.497
싶-0.487
l-0.449